© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54324
    Prev
    Next
    INDEX
    Explanations

    activ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     activity
    -0.36
    activity
    -0.35
     activities
    -0.34
    æ´»åĬ¨
    -0.33
     Activity
    -0.33
    .activity
    -0.32
    Activity
    -0.31
    .getActivity
    -0.29
    _activity
    -0.29
    .Activity
    -0.29
    POSITIVE LOGITS
    åħĢ
    0.28
    åį£
    0.28
    èĮ¬
    0.27
    ammer
    0.27
    hole
    0.26
    æľĭ
    0.26
    cycles
    0.26
    å¥ĩ迹
    0.25
    atrix
    0.25
    ometrics
    0.25
    Activations Density 0.018%

    No Known Activations